A software suite for deploying AI applications on the Cervell RISC-V NPU, built above the Aliado SDK and using Semidynamics’ ONNX Runtime Execution Provider.
Source & evidence
Supplier website Semidynamics today announced the Semidynamics Inferencing Tools, a new software suite that lets developers deploy AI applications on the Cervell RISC-V NPU in a fraction of the time. Sitting above the Aliado SDK and leveraging Semidynamics’ ONNX Runtime Execution Provider Semidynamics Technology Services SL website Checked 23 Oct 2026
A scalable, fully programmable RISC-V Neural Processing Unit combining CPU, vector and tensor capabilities; configurations range from C8 to C64.
Source & evidence
Supplier website Cervell™, a scalable and fully programmable Neural Processing Unit (NPU) built on RISC-V. Cervell combines CPU, vector, and tensor capabilities in a single, unified all-in-one architecture Semidynamics Technology Services SL website Checked 23 Oct 2026
A software development solution for Semidynamics hardware that includes compilation and debugging tools, emulators, and a library of routines.
Source & evidence
Supplier website the Aliado SDK enables quick and seamless development, debugging and fine-tuning of applications for Semidynamics hardware. It provides a complete software development solution including a compilation and debugging toolchain, emulators for functional testing of applications and a highly optimized library of common routines Semidynamics Technology Services SL website Checked 23 Oct 2026
An out-of-order 64-bit RISC-V core with integrated vector and tensor units and the Gazzillion memory subsystem.
Source & evidence
Supplier website the Inference Engine, an out-of-order 64-bit RISC-V core with integrated vector and tensor units and the Gazzillion memory subsystem built in Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics is developing racks for inference that combine CPU, vector and tensor compute in one architecture.
Source & evidence
Supplier website Semidynamics is developing AI accelerator racks for inference, bringing CPU, vector and tensor compute together in a single architecture. Semidynamics Technology Services SL website Checked 23 Oct 2026
A 3nm device combining multiple Inference Engines and capable of running standard Linux workloads.
Source & evidence
Supplier website the Inference SOC, a 3nm device combining multiple Inference Engines with the ability to run standard Linux workloads Semidynamics Technology Services SL website Checked 23 Oct 2026
A terabyte-scale AI inference unit for large models, with deterministic low-latency inference.
Source & evidence
Supplier website AI SYSTEMS - AIPU The World’s First Terabyte-Scale AI Inference Unit Inference for your largest models Enabling Deep thinking Deterministic low-latency inference Semidynamics Technology Services SL website Checked 23 Oct 2026
A board pairing a general-purpose host with Inference SOCs over a high-bandwidth fabric.
Source & evidence
Supplier website the Inference Board, pairing a general-purpose host with Inference SOCs over a high-bandwidth fabric engineered for persistent KV-cache residency across long context lengths Semidynamics Technology Services SL website Checked 23 Oct 2026
A software library included in the Semidynamics software stack.
Source & evidence
Supplier website Semidynamics software stack — including the Aliado Orchestrator and the AKL (Aliado Kernel Library) — runs the tools AI teams already use Semidynamics Technology Services SL website Checked 23 Oct 2026
Interview with Semidynamics CTO Iakovos Stamoulis: AI sovereignty and Europe’s opportunity / Inside the Semidynamics approach to AI inference
13 Oct 2026
Semidynamics is developing AI accelerator racks for inference, combining CPU, vector and tensor compute in one architecture.
Source & evidence
Supplier website Interview with Semidynamics CTO Iakovos Stamoulis: AI sovereignty and Europe’s opportunity / Inside the Semidynamics approach to AI inference Semidynamics is developing AI accelerator racks for inference, bringing CPU, vector and tensor compute together in a single architecture. [Publication date evidence: By David Harold | October 13th, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Rack: Why you need efficient memory, plus TOPS
5 Aug 2026
The article argues that TOPS alone is becoming less useful for understanding real rack performance.
Source & evidence
Supplier website Semidynamics Rack: Why you need efficient memory, plus TOPS TOPS are easy to print on a slide, easy to compare and a useful indication of how much work an accelerator can do. But at Semidynamics we think that number is becoming less useful on its own as a way to understand real rack performance. [Publication date evidence: By Iakovos Stamoulis | August 5th, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
Elevating Verification Rigour: Why Semidynamics Partnered with LUBIS EDA
14 Jul 2026
The article discusses verification challenges in building high-performance AI inference systems and Semidynamics' partnership with LUBIS EDA.
Source & evidence
Supplier website Elevating Verification Rigour: Why Semidynamics Partnered with LUBIS EDA At Semidynamics, the engineering team is dedicated to building high-performance AI inference systems, from terabyte-scale AIPUs to custom CPU and NPU cores. Operating at this level of complexity demands an uncompromising approach to quality. [Publication date evidence: By Miquel Izquierdo | July 14th, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
AI compute is only as useful as the memory architecture feeding it — Semidynamics brings its full inference stack to ISC HPC 2026
19 Jun 2026
Semidynamics announced that it would present its memory-centric inference platform, from RISC-V core to liquid-cooled OCP-compliant rack, at ISC High Performance 2026.
Source & evidence
Supplier website Barcelona, Spain — June 18th, 2026 — Building high-performance AI silicon is necessary but no longer sufficient: the compute is only useful if the memory system can keep it fed. That is the argument Semidynamics CEO Roger Espasa will bring to ISC High Performance 2026 in Hamburg (23–25 June, booth A22, Hall H), where the Barcelona-based company — which taped out its first 3nm chip with TSMC in December 2025 — will present its plans for a complete memory-centric inference platform, from RISC-V core to liquid-cooled, OCP-compliant rack, at a major HPC trade show for the first time. [Publication date evidence: June 19th, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics and SiPearl Announce Strategic Cooperation to Develop EU-Sovereign Rack-Scale AI Compute Platform
7 May 2026
Semidynamics and SiPearl announced a strategic partnership to develop a European rack-scale AI compute platform for large-scale cloud inference.
Source & evidence
Supplier website Semidynamics, an advanced computing company developing memory-centric AI infrastructure for large-scale inference, and SiPearl, the European fabless designer of high-performance energy-efficient CPUs for sovereign supercomputing, AI and data centres, have entered into a strategic partnership to develop a European rack‑scale AI compute platform dedicated to large‑scale AI inference in the cloud. [Publication date evidence: May 7th, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Secures a Strategic Investment to Advance Memory-Centric AI Inference Chips
8 Apr 2026
Semidynamics announced a strategic investment from SK hynix to support collaboration on next-generation AI infrastructure and memory technologies.
Source & evidence
Supplier website Barcelona, Spain — April 8th, 2026 — Semidynamics, an advanced computing company developing memory-centric AI infrastructure for large-scale inference, today announced a strategic investment from SK hynix, one of the world's leading memory manufacturers. [Publication date evidence: April 8th, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Unveils 3nm AI Inference Silicon and Full-Stack Systems
3 Feb 2026
Semidynamics announced a roadmap for inference silicon and vertically integrated systems, including chips, boards and rack-level systems.
Source & evidence
Supplier website Barcelona, Spain — February 3rd, 2026 — Semidynamics today announced its expansion into full-stack AI infrastructure, unveiling a strategic roadmap to deliver high-performance inference silicon and vertically integrated systems. Building on its proprietary architecture, the company is developing chips, boards, and rack-level systems designed for the most demanding AI workloads in next-generation data centers. [Publication date evidence: February 3rd, 2026] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Welcomes Iakovos Stamoulis as Chief Technology Officer
2 Dec 2025
Semidynamics announced the appointment of Iakovos Stamoulis as CTO, where he would lead the company’s technology strategy.
Source & evidence
Supplier website Semidynamics today announced the appointment of Iakovos Stamoulis as Chief Technology Officer (CTO). [Publication date evidence: December 2nd, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Your AI Model is Already Free
19 Nov 2025
The article discusses the assumption that high-performance deployment must remain CUDA-centric after development and training on GPUs.
Source & evidence
Supplier website Your AI Model is Already Free Most deployments follow the same pattern: you build and train on GPUs using a de-facto standard environment based on CUDA for R&D. Then, almost by habit, you may assume deployment also has to be CUDA-centric if you want high performance. [Publication date evidence: By Pedro Almada | November 19th, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Inferencing Tools Accelerate AI App Deployment on Cervell NPU
22 Oct 2025
Semidynamics announced software tools for deploying AI applications on the Cervell RISC-V NPU.
Source & evidence
Supplier website Semidynamics today announced the Semidynamics Inferencing Tools, a new software suite that lets developers deploy AI applications on the Cervell RISC-V NPU in a fraction of the time. [Publication date evidence: October 22nd, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Cervell and the Changing Shape of AI Infrastructure
1 Sept 2025
The article discusses inference costs, memory bottlenecks, and efficiency in AI infrastructure.
Source & evidence
Supplier website Cervell and the Changing Shape of AI Infrastructure AI infrastructure is no longer defined by how much raw compute you can deliver, but by how efficiently you can run it at scale. Hyperscalers are under pressure from ballooning inference costs, memory bottlenecks, and the thermal and power ceilings of their datacenters. [Publication date evidence: By Volker Politz | September 1st, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
AI runs on vectors
10 Jul 2025
The article describes vectorizing data as a shift in enterprise data and AI strategy.
Source & evidence
Supplier website AI runs on vectors A key trend in AI recently has been the emphasis on vectorizing data. That is not a technical recommendation, but rather a fundamental shift in enterprise data and AI strategy. [Publication date evidence: By Pedro Marcuello | July 10th, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
One Instruction Stream, Infinite Possibilities: The Cervell™ Approach to Reinventing the NPU
11 Jun 2025
The article introduces Cervell™ as a new kind of NPU and discusses changing AI models and traditional NPU designs.
Source & evidence
Supplier website One Instruction Stream, Infinite Possibilities: The Cervell™ Approach to Reinventing the NPU AI is evolving faster than the chips designed to run it. Models like large language transformers and generative networks are shifting rapidly–while silicon development cycles remain long and rigid. Traditional NPUs, built around proprietary instruction sets and opaque compilers, simply can’t keep up. [Publication date evidence: By Volker Politz | June 11th, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Announces Cervell™ All-in-One RISC-V NPU Delivering Scalable AI Compute for Edge and Datacenter Applications
6 May 2025
Semidynamics announced Cervell, a scalable and fully programmable RISC-V NPU combining CPU, vector and tensor capabilities.
Source & evidence
Supplier website Semidynamics, the only provider of fully customizable RISC-V processor IP, announces Cervell™, a scalable and fully programmable Neural Processing Unit (NPU) built on RISC-V. Cervell combines CPU, vector, and tensor capabilities in a single, unified all-in-one architecture [Publication date evidence: May 6th, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Vision-Language Models (VLM) – the next big thing in AI?
27 Mar 2025
The article discusses Vision-Language Models and their use in areas including autonomous vehicles, robotics, and AI-driven assistants.
Source & evidence
Supplier website Vision-Language Models (VLM) – the next big thing in AI? AI has changed a lot in the last ten years. In 2012, convolutional neural networks (CNNs) were the state of the art for computer vision. Then around 2020 vison transformers (ViTs) redefined machine learning. Now, Vision-Language Models (VLMs) are changing the game again—blending image and text understanding to power everything from autonomous vehicles to robotics to AI-driven assistants. [Publication date evidence: By Semidynamics | March 27th, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics’ Aliado SDK Accelerates AI Development for RISC-V with Seamless ONNX Integration
4 Mar 2025
Semidynamics announced support for ONNX Runtime and availability of its RISC-V software development kit, Aliado.
Source & evidence
Supplier website Semidynamics, the leading IP company for high performance, AI-enabled, RISC-V processors, has announced its support for the ONNX Runtime and the availability of its RISC-V Software Development Kit (SDK), Aliado. [Publication date evidence: March 4, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Baya Systems and Semidynamics Collaborate to Accelerate RISC-V System-on-Chip Development
25 Feb 2025
Semidynamics and Baya Systems announced a collaboration integrating Semidynamics RISC-V processor IP cores with Baya Systems’ WeaveIP Network on Chip system IP.
Source & evidence
Supplier website The collaboration integrates Semidynamics’ family of 64-bit RISC-V processor IP cores, known for their exceptional memory bandwidth and configurability, with Baya Systems’ innovative WeaveIP™ Network on Chip (NoC) system IP. [Publication date evidence: February 25, 2025] Semidynamics Technology Services SL website Checked 23 Oct 2026
Gazzillion Misses - Making the Memory Wall Irrelevant
9 Sept 2024
The article describes memory-bound applications and the time and energy spent moving data.
Source & evidence
Supplier website Gazzillion Misses - Making the Memory Wall Irrelevant Computer programs mainly move data around. In the meantime, they do some computations on the data but the bulk of execution time and energy is spent moving data around. In computer jargon we say that applications tend to be memory bound: this means that memory is the main performance limiting factor. [Publication date evidence: By José María Arnau | September 9th, 2024] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics Recognized as a Key Innovator in the RISC-V Ecosystem
1 Aug 2024
The article says Semidynamics was featured in an Omdia report, “Startups and Unique Players Continue to Energize the RISC-V Ecosystem: 10 to Watch.”
Source & evidence
Supplier website Semidynamics Recognized as a Key Innovator in the RISC-V Ecosystem We are delighted to share that Semidynamics has been featured in the latest Omdia report, "Startups and Unique Players Continue to Energize the RISC-V Ecosystem: 10 to Watch." [Publication date evidence: By Semydamics | August 1st, 2024] Semidynamics Technology Services SL website Checked 23 Oct 2026
Semidynamics shortlisted for Semiconductor Product of the Year (Digital) in Elektra Awards 2023
20 Sept 2023
Semidynamics was named a finalist in the Elektra Awards 2023 Semiconductor Product of the Year (Digital) category for its Atrevido processor core.
Source & evidence
Supplier website Semidynamics is a finalist in this year’s Elektra Awards in the category of Semiconductor Product of the Year (Digital). This is for the company’s new Atrevido 64-bit RISC-V IP processor core. [Publication date evidence: September 20th, 2023] Semidynamics Technology Services SL website Checked 23 Oct 2026
Evidence & freshness
Every claim keeps its source. Company-reported information and independent verification are labelled separately. Spot something wrong? .
Inference Rack · AKL (Aliado Kernel Library) · News: AI compute is only as useful as the memory architecture feeding it — Semidynamics brings its full inference stack to ISC HPC 2026 · News: Semidynamics and SiPearl Announce Strategic Cooperation to Develop EU-Sovereign Rack-Scale AI Compute Platform · News: Semidynamics Secures a Strategic Investment to Advance Memory-Centric AI Inference Chips · News: Semidynamics Unveils 3nm AI Inference Silicon and Full-Stack Systems · News: Semidynamics Welcomes Iakovos Stamoulis as Chief Technology Officer · News: Semidynamics Inferencing Tools Accelerate AI App Deployment on Cervell NPU · News: Semidynamics Announces Cervell™ All-in-One RISC-V NPU Delivering Scalable AI Compute for Edge and Datacenter Applications · News: Semidynamics’ Aliado SDK Accelerates AI Development for RISC-V with Seamless ONNX Integration · News: Baya Systems and Semidynamics Collaborate to Accelerate RISC-V System-on-Chip Development
Supports 14 facts: Company name · Description · AI accelerator racks · Location: Barcelona, Spain · News: Interview with Semidynamics CTO Iakovos Stamoulis: AI sovereignty and Europe’s opportunity / Inside the Semidynamics approach to AI inference · News: Semidynamics Rack: Why you need efficient memory, plus TOPS · News: Elevating Verification Rigour: Why Semidynamics Partnered with LUBIS EDA · News: Your AI Model is Already Free
6 more
News: Cervell and the Changing Shape of AI Infrastructure · News: AI runs on vectors · News: One Instruction Stream, Infinite Possibilities: The Cervell™ Approach to Reinventing the NPU · News: Vision-Language Models (VLM) – the next big thing in AI? · News: Gazzillion Misses - Making the Memory Wall Irrelevant · News: Semidynamics Recognized as a Key Innovator in the RISC-V Ecosystem
Supports 3 facts: Company name · Location: Barcelona, Spain · News: Semidynamics shortlisted for Semiconductor Product of the Year (Digital) in Elektra Awards 2023
What to confirm
A starting point for your supplier conversation.
Manufacturing processesNo source confirms this yet
Services and capabilitiesNo source confirms this yet
CertificationsNo source confirms this yet
Order quantity & lead timeConfirm directly with the supplier
AI-inferred Based only on `company`, does this company offer engineering or product-design services for customers' products (hardware, firmware, PCB layout, product development)?